aleatoric uncertainty
Uncertainty that arises from inherent randomness in the data or environment, as opposed to lack of knowledge about the model (epistemic uncertainty).
- Architectural and Inferential Inductive Biases for Exchangeable Sequence Modeling
- Enhancing Vision-Language Model Reliability with Uncertainty-Guided Dropout Decoding
- MetaKoopman: Bayesian Meta-Learning of Koopman Operators for Modeling Structured Dynamics under Distribution Shifts
- PRESCRIBE: Predicting Single-Cell Responses with Bayesian Estimation
- Plug-and-play Feature Causality Decomposition for Multimodal Representation Learning
- Rethinking Approximate Gaussian Inference in Classification
- STACI: Spatio-Temporal Aleatoric Conformal Inference
- Towards Robust Uncertainty Calibration for Composed Image Retrieval
- UGG-ReID: Uncertainty-Guided Graph Model for Multi-Modal Object Re-Identification
- Uncertainty-Informed Meta Pseudo Labeling for Surrogate Modeling with Limited Labeled Data
- Variational Uncertainty Decomposition for In-Context Learning
- Vicinal Label Supervision for Reliable Aleatoric and Epistemic Uncertainty Estimation